A neural network has identified eleven asteroids once thought to be benign that may actually come close enough to hit Earth.

These 11 space rocks, each measuring more than 100 metres across, are listed in a NASA database as non-hazardous objects. Don’t worry about them, in other word.

However, AI software – developed by researchers at Leiden University in the Netherlands, and dubbed the Hazardous Object Identifier – has singled out the asteroids, predicting they could come within 0.05 astronomical units (7.5 million kilometres, 4.7 million miles) of terra firma. By that definition, these asteroids should be labelled as potentially hazardous objects, not non-hazardous.

Although that sounds a little alarming, they are still unlikely to slam into our fragile world, since 0.05 astronomical units is a wide margin. Just because something’s declared a hazardous object, be it by a human or machine-learning code, that doesn’t mean it’s going to pummel us to death… sadly.

To train the neural network, the researchers simulated hundreds of thousands of asteroid collisions with Earth, recording the space boulders’ motion over time using the ALICE supercomputer cluster at the university.

Data describing each asteroid’s properties and trajectories were then fed into the machine-learning software so that it could discern and learn to spot common features that hint that an asteroid may crash into Earth. In other words, the software was taught to pick up on patterns in the data common among asteroids that would hit Earth and identify them as such. Each asteroid was encoded as a vector of variables defining the semi-major axis, eccentricity, and inclination of its orbit, as well as its mean speed, and angular momentum.

“If you rewind the clock, you will see the well-known asteroids land again on Earth,” Simon Portegies Zwart, co-author of the paper and an astronomy professor at Leiden, said last week. “This way you can make a library of the orbits of asteroids that landed on Earth.”

The eggheads also trained the model on data describing hundreds of thousands of real asteroids, taken from NASA’s dastcom5 dataset. Unlike the simulated asteroids, these rocks are not expected to crash into Earth, and should help the software determine benign objects.

A paper published [prepint PDF] in the Astronomy & Astrophysics journal this month shows that the model was able to detect 13,258 potentially hazardous objects after running it on a test dataset.

However, since the test data contained a mixture of simulated and real asteroids, that number isn’t very useful. “A total of 13,258 asteroids identified by HOI [the AI software] as known impactors are not listed by NASA as potentially hazardous objects,” the paper said. Sure, the majority of those asteroids aren’t listed by NASA, because they don’t, er, exist, it seems.

Instead, a better measurement is to see how the model performed on unseen real data. The researchers tested the neural network on nearly 2,000 asteroids listed by NASA as potentially hazardous, and the code managed to correctly identify 90.99 per cent of them without having been explicitly trained on this set of rocks. That also means it missed one in ten that humans previously identified.

What’s intriguing, though, is that it detected eleven non-hazardous asteroids in our Solar System that will come closer than ten times the distance between the Earth and the Moon. If any of them were to strike our planet, that would be not pleasant.

“For perspective, Tunguska object which flattened 2,000 square kilometers of forest in Siberia was estimated to have a diameter of between 50 and 80 meters,” according to the paper. The identified asteroids – 2005 RV24, 2008 UV99, 2011 BU10, 2011 HH1, 2011 WC44, 2013 AG76, 2014 GL35, 2014 TW57, 2014 WD365, 2017 DQ36, and 2017 JE3 – are bigger than Tunguska.

Don’t panic just yet: the machine-learning software reckoned the prangs may occur between the years 2131 and 2923. It’ll be difficult for us right now to verify its predictions, as the crashes are expected to take place hundreds of years from now.

The researchers noted that NASA probably missed these asteroids as hazardous because their observed orbits are so uncertain. Calculating the probabilities of these impacting Earth, therefore, is likely to be difficult.

“We generated a short list of network identified potential impactors which NASA does not label as potentially hazardous objects, mainly because the observed orbital elements are so uncertain that NASA’s Monte Carlo approach to determine their Earth-striking probability fails,” the paper concluded. ®

Sponsored: Detecting cyber attacks as a small to medium business